• Corpus ID: 8543353

The Retinex Theory of Color Vision SCIENTIFIC AMERICAN

@inproceedings{Land2009TheRT,
  title={The Retinex Theory of Color Vision SCIENTIFIC AMERICAN},
  author={Edwin Herbert Land},
  year={2009}
}
  • E. Land
  • Published 2009
  • Computer Science
The review of color balance method for UAV image By COMPUTER technology
TLDR
This paper reviews and compares the classic color balance methods of brightness equalization currently and gives a detailed explanation and effect of the application of each method.
Green Stability Assumption: Unsupervised Learning for Statistics-Based Illumination Estimation
TLDR
The green stability assumption is proposed that can be used to fine-tune the values of some common illumination estimation methods by using only non-calibrated images, and the obtained accuracy is practically the same as when training on calibrated images, but the whole process is much faster since calibration is not required and thus time is saved.
Unsupervised Learning for Color Constancy
TLDR
An unsupervised learning-based method is proposed that learns its parameter values after approximating the unknown ground-truth illumination of the training images, thus avoiding calibration and outperforms all statistics-based and many learning- based methods in terms of accuracy.
Transfer Learning for Color Constancy via Statistic Perspective
TLDR
Experimental results show the TLCC has overcome the data limitation and model degradation, outperforming the state-of-the-art performance on popular benchmarks, and prove theTLCC is capable of learning new scenes information from sRGB data to improve accuracy on the RAW images with similar scenes.
Derivative feature and residual spatial attention for low-light image enhancement
  • Qihan Li, S. Kamata
  • Computer Science
    International Conference on Signal Processing Systems
  • 2022
TLDR
This work builds a Retinex theorybased neural network, which decomposes the input images into an illumination map and a reflectance map and uses the Gaussian blur for reducing the problem of brightness enhancement degradation and build the Residual Spatial Attention Block (RSAB) to enlarge the volume and increase the capability of pixel-to-pixel mapping.
Embedded low illumination enhanced network for object detection
TLDR
An embedded low illumination enhanced network based on the Scale-YOLOv4 object detection network is proposed, iteratively generating enhancement images with different illumination levels, and among the enhanced images, automatically selecting the one which is best suitable for target detection, and adding a noise removal module to eliminate the generated noise.
Semantically Contrastive Learning for Low-light Image Enhancement
TLDR
This paper proposes an effective semantically contrastive learning paradigm for LLE, SCL-LLE, which surpasses the state-of-the-arts LLE models over six independent cross-scenes datasets and its potential to benefit the downstream semantic segmentation under extremely dark conditions is discussed.
Degrade is Upgrade: Learning Degradation for Low-light Image Enhancement
TLDR
A novel two-step generation network for degradation learning and content refinement, which is not only superior to one-step methods, but also capable of synthesizing sufficient paired samples to benefit the model training.
Lane Line Extraction in Raining Weather Images by Ridge Edge Detection with Improved MSR and Hessian Matrix
TLDR
By testing hundreds of images of the lane lines at raining weather and by comparing several traditional image enhancement and segmentation algorithms, the new method of thelane line detection can produce the satisfactory results.
Deep Learning-Enabled Low-light Image Enhancement In Maritime Video Surveillance
TLDR
The experimental results show that the depth network proposed in this paper improves the brightness and contrast with the monitoring images of the inland river bridge area and further improves the monitoring effect ofThe inland river bridges area, thus providing a guarantee of water traffic safety in the bridge area to a certain extent.
...
...